Dynamic, cognitive hybrid method and system for indoor sensing and positioning

1. A computer-implemented method for dynamic, cognitive hybrid positioning within an indoor environment, the method comprising:

receiving fingerprinting training data corresponding to the indoor environment, trilateration data corresponding to the indoor environment, triangulation data corresponding to the indoor environment, or a combination of the fingerprinting training data, the trilateration data, and/or the triangulation data;

estimating a layout of the indoor environment based at least in part on the fingerprinting training data;

classifying at least first and second areas of the estimated layout according to predetermined area types selected from the group consisting of: inaccessible spaces, closed spaces, open spaces, walls, hallways, and undetermined spaces, wherein the first area comprises a first of the predetermined area types and the second area comprises a second of the predetermined area types that is different from the first predetermined area type;

determining a respective positioning technique to utilize for each area of the estimated layout, wherein the respective positioning technique is determined based at least in part on the area type and the determining comprises:

determining a first positioning technique for the first area, and

determining a second positioning technique that is different from the first positioning technique for the second area; and

estimating a first location of a user sensing device in the first area using the first positioning technique and estimating a second location of the user sensing device in the second area using the second positioning technique.

2. The method as recited in claim 1 , wherein the predetermined area types are classified according to one or more factors selected from the group consisting of: a density of connections characterized by strong signal strength within a predetermined area, a density of connections characterized by weak signal strength within the predetermined area, and combinations thereof.

3. The method as recited in claim 1 , wherein the fingerprinting training data comprise:

a plurality of first (X, Y) locations, each first (X, Y) location corresponding to a location of one of a plurality of location sensors deployed throughout the indoor environment;

a plurality of second (X, Y) locations, each second (X, Y) location corresponding to a location of a sensing device upon the sensing device receiving one of a plurality of signals from one of the location sensors;

identifying information for each of the plurality of location sensors;

received signal strength indicator (RSSI) information corresponding to each of the plurality of signals received by the sensing device; and

a plurality of timestamps, each timestamp corresponding to a time of receipt of one of the signals, by the sensing device.

4. The method as recited in claim 1 , wherein the trilateration data comprise:

a plurality of (X, Y) coordinate pairs, each (X, Y) coordinate pair corresponding to a location one of a plurality of location sensors deployed throughout the indoor environment; and

a plurality of distances, each distance describing a distance between a sensing device and one of the location sensors at a time of the sensing device receiving a signal from the one of the location sensors; and

wherein the triangulation data comprise:

the plurality of (X, Y) coordinate pairs; and

a plurality of bearings, each bearing describing an angle between the sensing device and one of the location sensors at a time of receiving a signal from the one of the location sensors.

5. The method as recited in claim 1 , wherein the positioning technique is selected from the group consisting of: trilateration, triangulation, and combinations thereof.

6. A system for dynamic, cognitive hybrid positioning within an indoor environment, comprising:

a processor; and

logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to:

perform the method of claim 1 .

7. The system as recited in claim 6 , wherein the predetermined area types are selected from the group consisting of: inaccessible spaces, closed spaces, opens spaces, walls, hallways, and undetermined spaces; and

wherein the predetermined area types are classified according to one or more factors selected from the group consisting of: a density of connections characterized by strong signal strength within a predetermined area, a density of connections characterized by weak signal strength within the predetermined area, and combinations thereof.

8. The system as recited in claim 6 , wherein the fingerprinting training data comprise:

a plurality of first (X, Y) locations, each first (X, Y) location corresponding to a location of one of a plurality of location sensors deployed throughout the indoor environment;

a plurality of second (X, Y) locations, each second (X, Y) location corresponding to a location of a sensing device upon the sensing device receiving one of a plurality of signals from one of the location sensors;

identifying information for each of the plurality of location sensors;

received signal strength indicator (RSSI) information corresponding to each of the plurality of signals received by the sensing device; and

a plurality of timestamps, each timestamp corresponding to a time of receipt of one of the signals, by the sensing device.

9. The system as recited in claim 6 , wherein the trilateration data comprise:

a plurality of (X, Y) coordinate pairs, each (X, Y) coordinate pair corresponding to a location one of a plurality of location sensors deployed throughout the indoor environment; and

a plurality of distances, each distance describing a distance between a sensing device and one of the location sensors at a time of the sensing device receiving a signal from the one of the location sensors; and

wherein the triangulation data comprise:

the plurality of (X, Y) coordinate pairs; and

a plurality of bearings, each bearing describing an angle between the sensing device and one of the location sensors at a time of receiving a signal from the one of the location sensors.

10. A computer program product for dynamic, cognitive hybrid positioning within an indoor environment includes a non-transitory computer readable storage medium having program instructions embodied therewith, wherein the program instructions are executable by a processor to cause the processor to perform a method comprising:

receiving fingerprinting training data corresponding to the indoor environment;

estimating a layout of the indoor environment based at least in part on the fingerprinting training data;

classifying at least first and second areas of the estimated layout according to predetermined area types selected from the group consisting of: inaccessible spaces, closed spaces, open spaces, walls, hallways, and undetermined spaces, wherein the first area comprises a first of the predetermined area types and the second area comprises a second of the predetermined area types that is different from the first predetermined area type;

determining a respective positioning technique to utilize within each area of the estimated layout, wherein the positioning technique is determined based at least in part on the area type and the determining comprises:

determining a first positioning technique for the first area, and

determining a second positioning technique that is different from the first positioning technique for the second area; and

estimating a first location of a user sensing device in the first area using the first positioning technique and estimating a second location of the user sensing device in the second area using the second positioning technique.

11. The computer program product as recited in claim 10 , wherein the predetermined area types are classified according to one or more factors selected from the group consisting of: a density of connections characterized by strong signal strength within a predetermined area, a density of connections characterized by weak signal strength within the predetermined area, and combinations thereof.

12. The computer program product as recited in claim 10 , wherein the fingerprinting training data comprise:

a plurality of first (X, Y) locations, each first (X, Y) location corresponding to a location of one of a plurality of location sensors deployed throughout the indoor environment;

a plurality of second (X, Y) locations, each second (X, Y) location corresponding to a location of a sensing device upon the sensing device receiving one of a plurality of signals from one of the location sensors;

identifying information for each of the plurality of location sensors;

received signal strength indicator (RSSI) information corresponding to each of the plurality of signals received by the sensing device; and

a plurality of timestamps, each timestamp corresponding to a time of receipt of one of the plurality of signals, by the sensing device.

13. The computer program product as recited in claim 10 , comprising receiving trilateration data corresponding to the indoor environment, wherein the trilateration data comprise:

a plurality of (X, Y) coordinate pairs, each (X, Y) coordinate pair corresponding to a location one of a plurality of location sensors deployed throughout the indoor environment; and

a plurality of distances, each distance describing a distance between a sensing device and one of the location sensors at a time of the sensing device receiving a signal from the one of the location sensors.

14. A computer-implemented method for dynamic, cognitive hybrid positioning within an indoor environment, the method comprising:

receiving fingerprinting training data corresponding to the indoor environment;

receiving at least one type of data selected from the group consisting of trilateration data corresponding to the indoor environment and triangulation data corresponding to the indoor environment;

estimating a layout of the indoor environment based at least in part on the fingerprinting training data;

classifying at least a first area and a second area of the estimated layout according to a respective one of predetermined area types selected from the group consisting of: inaccessible spaces, closed spaces, open spaces, walls, hallways, and undetermined spaces, wherein the first area comprises a first of the predetermined area types and the second area comprises a second of the predetermined area types that is different from the first predetermined area type;

determining a respective positioning technique to utilize within each area of the estimated layout, wherein the respective positioning technique is determined based at least in part on the respective one of the predetermined area types and the determining comprises:

determining a first positioning technique for the first area, and

determining a second positioning technique that is different from the first positioning technique for the second area; and

evaluating, using a similarity scoring metric or an error metric, a performance of a fingerprinting technique using the fingerprinting training data and at least one of a trilateration technique using the trilateration data and a triangulation technique using the triangulation data within one of the areas of the estimated layout, wherein the one of the areas of the estimated layout is characterized by having the predetermined area type “undetermined”.

15. The method as recited in claim 14 , wherein the predetermined area types are classified according to one or more factors selected from the group consisting of: a density of connections characterized by strong signal strength within a predetermined area, a density of connections characterized by weak signal strength within the predetermined area, and combinations thereof.

16. The method as recited in claim 14 , comprising receiving trilateration data corresponding to the indoor environment and triangulation data corresponding to the indoor environment; wherein the trilateration data comprise:

a plurality of (X, Y) coordinate pairs, each (X, Y) coordinate pair corresponding to a location one of a plurality of location sensors deployed throughout the indoor environment; and

a plurality of distances, each distance describing a distance between a sensing device and one of the location sensors at a time of the sensing device receiving a signal from the one of the location sensors; and

wherein the triangulation data comprise:

the plurality of (X, Y) coordinate pairs; and

a plurality of bearings, each bearing describing an angle between the sensing device and one of the location sensors at a time of receiving a signal from the one of the location sensors.

17. The method as recited in claim 14 , wherein the positioning technique is selected from the group consisting of: trilateration, triangulation, and combinations thereof.

18. The method as recited in claim 14 , comprising estimating a location of a user sensing device using the one or more positioning techniques.